Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and GeneralizationDownload PDF

Published: 09 Nov 2021, Last Modified: 14 Jul 2024NeurIPS 2021 PosterReaders: Everyone
Keywords: Multi-agent System, Multi-armed Bandits, Decentralized Learning
Abstract: Despite the significant interests and many progresses in decentralized multi-player multi-armed bandits (MP-MAB) problems in recent years, the regret gap to the natural centralized lower bound in the heterogeneous MP-MAB setting remains open. In this paper, we propose BEACON -- Batched Exploration with Adaptive COmmunicatioN -- that closes this gap. BEACON accomplishes this goal with novel contributions in implicit communication and efficient exploration. For the former, we propose a novel adaptive differential communication (ADC) design that significantly improves the implicit communication efficiency. For the latter, a carefully crafted batched exploration scheme is developed to enable incorporation of the combinatorial upper confidence bound (CUCB) principle. We then generalize the existing linear-reward MP-MAB problems, where the system reward is always the sum of individually collected rewards, to a new MP-MAB problem where the system reward is a general (nonlinear) function of individual rewards. We extend BEACON to solve this problem and prove a logarithmic regret. BEACON bridges the algorithm design and regret analysis of combinatorial MAB (CMAB) and MP-MAB, two largely disjointed areas in MAB, and the results in this paper suggest that this previously ignored connection is worth further investigation.
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
TL;DR: This work closed the regret gap from centralized performance in decentralized heterogeneous multi-player multi-armed bandits, and extended the study from the linear reward function to general reward functions.
Supplementary Material: pdf
Code: https://github.com/ShenGroup/MPMAB_BEACON
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/heterogeneous-multi-player-multi-armed/code)
11 Replies

Loading